Multiclass learnability does not imply sample compression
From MaRDI portal
Cites work
- A characterization of multiclass learnability
- A decision-theoretic generalization of on-line learning and an application to boosting
- A generalization of Sauer's lemma
- A theory of PAC learnability of partial concept classes
- A theory of the learnable
- Boosting a weak learning algorithm by majority
- Characterizations of learnability for classes of \(\{0,\dots,n\}\)-valued functions
- Clique versus independent set
- Density and dimension
- scientific article; zbMATH DE number 736299 (Why is no real title available?)
- Learnability and the Vapnik-Chervonenkis dimension
- Low-sensitivity functions from unambiguous certificates
- Lower bounds for clique vs. independent set
- Multiclass learnability and the ERM principle
- On the Uniform Convergence of Relative Frequencies of Events to Their Probabilities
- Sample Compression Schemes for VC Classes
- Teaching and Compressing for Low VC-Dimension
- Unambiguous DNFs and Alon-Saks-Seymour
This page was built for publication: Multiclass learnability does not imply sample compression
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q7017078)
